Papers › 75 Languages, 1 Model: Parsing Universal Dependencies Universally

75 Languages, 1 Model: Parsing Universal Dependencies Universally

3 Apr 2019IJCNLP 2019 11arXiv:1904.02099archive 2025-07-28

Dan Kondratyuk, Milan Straka

We present UDify, a multilingual multi-task model capable of accurately predicting universal part-of-speech, morphological features, lemmas, and dependency trees simultaneously for all 124 Universal Dependencies treebanks across 75 languages. By leveraging a multilingual BERT self-attention model pretrained on 104 languages, we found that fine-tuning it on all datasets concatenated together with simple softmax classifiers for each UD task can result in state-of-the-art UPOS, UFeats, Lemmas, UAS, and LAS scores, without requiring any recurrent or language-specific components. We evaluate UDify for multilingual learning, showing that low-resource languages benefit the most from cross-linguistic annotations. We also evaluate for zero-shot learning, with results suggesting that multilingual training provides strong UD predictions even for languages that neither UDify nor BERT have ever been trained on. Code for UDify is available at https://github.com/hyperparticle/udify.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="1904.02099")

Code

Syntology Ran 0 of 12 code samples harvested from 1 repository linked to this paper; 12 have no recorded run.

By repository: official repository: 12 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

hyperparticle/udify officialmentioned in papermentioned on GitHubpytorchMIT report
ahmetustun/udapter mentioned on GitHubpytorch report
idiap/g2g-transformer mentioned on GitHubpytorchGPL-2.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

12 samples harvested; 0 ran; 0 honoured the contract we drafted; 12 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

12unverified

Licence: 0 of the 12 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from hyperparticle/udify. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

apply_lemma_rule hyperparticle/udify/udify/dataset_readers/lemma_edit.py official repository unverified MIT (permissive) · dd23f8f805a509d4 · report
distance hyperparticle/udify/udify/dataset_readers/evaluate_2019_task2.py official repository unverified MIT (permissive) · 665f20ac94b4aa09 · report
evaluate hyperparticle/udify/udify/dataset_readers/conll18_ud_eval.py official repository unverified MIT (permissive) · 245d8f594031798b · report
gen_lemma_rule hyperparticle/udify/udify/dataset_readers/lemma_edit.py official repository unverified MIT (permissive) · d56f4a572f75726c · report
get_ud_treebank_files hyperparticle/udify/udify/util.py official repository unverified MIT (permissive) · 41be2131e0bb7615 · report
get_ud_treebank_names hyperparticle/udify/udify/util.py official repository unverified MIT (permissive) · e9c1c9c44d53c7dc · report
load_conllu hyperparticle/udify/udify/dataset_readers/conll18_ud_eval.py official repository unverified MIT (permissive) · 7db5fbed47b0c09d · report
load_conllu_file hyperparticle/udify/udify/dataset_readers/conll18_ud_eval.py official repository unverified MIT (permissive) · d6122a3c08a641ad · report
manipulate_data hyperparticle/udify/udify/dataset_readers/evaluate_2019_task2.py official repository unverified MIT (permissive) · 6b04a2e33ab50ab7 · report
min_edit_script hyperparticle/udify/udify/dataset_readers/lemma_edit.py official repository unverified MIT (permissive) · 277006db04b14f51 · report
sequence_cross_entropy hyperparticle/udify/udify/models/tag_decoder.py official repository unverified MIT (permissive) · dff441cf8da0ff92 · report
set_equal hyperparticle/udify/udify/dataset_readers/evaluate_2019_task2.py official repository unverified MIT (permissive) · f5cf6da83aa49097 · report

Tasks

Dependency ParsingZero-Shot Learningmodel

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Dependency Parsing French GSD UDify LAS 91.45 #2 of 2 Archive leaderboard report
Dependency Parsing French GSD UDify UAS 93.60 #2 of 2 Archive leaderboard report
Dependency Parsing ParTUT UDify LAS 88.06 #2 of 2 Archive leaderboard report
Dependency Parsing ParTUT UDify UAS 90.55 #2 of 2 Archive leaderboard report
Dependency Parsing Sequoia Treebank UDify LAS 90.05 #2 of 2 Archive leaderboard report
Dependency Parsing Sequoia Treebank UDify UAS 92.53 #2 of 2 Archive leaderboard report
Dependency Parsing Spoken Corpus UDify LAS 80.01 #2 of 2 Archive leaderboard report
Dependency Parsing Spoken Corpus UDify UAS 85.24 #2 of 2 Archive leaderboard report
Dependency Parsing Universal Dependencies UDify LAS 80.43 #2 of 6 Archive leaderboard report
Dependency Parsing Universal Dependencies UDify UAS 85.69 #2 of 6 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

AdamAttentionAttention DropoutBERTDense ConnectionsDropoutLayer NormalizationLinear LayerLinear Warmup With Linear DecayMulti-Head AttentionResidual ConnectionSoftmaxWeight DecayWordPiece

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections